AI Paper Atlas

Research map / 3D vision / Face and shape

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Chongjie Ye, Yushuang Wu, Ziteng Lu, Jiahao Chang, Xiaoyang Guo, Jiaqing Zhou, Hao Zhao, Xiaoguang Han

ICCV 2025 · 3D vision › Face and shape · approach: Textured mesh generation · 93 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DetailVerse synthetic data to image-normal training (ablation)NiRNE · LUCES-MVNE: 22.209 -> 21.837Improved
add DetailVerse synthetic data to image-normal training (ablation)NiRNE · LUCES-MVSNE: 28.324 -> 26.628Improved
add domain-specific training (real then synthetic fine-tuning of noisy stream) (ablation)NiRNE · LUCES-MVSNE: 29.690 -> 26.628Improved
add domain-specific training (ablation)NiRNE · LUCES-MVNE: 23.288 -> 21.837Improved
add dual-stream architecture (ablation)NiRNE · LUCES-MVSNE: 29.520 -> 26.628Improved
add dual-stream architecture (ablation)NiRNE · LUCES-MVNE: 21.918 -> 21.837No clear effect
add DS, DST, DV together (full vs w/o all) (ablation)NiRNE · LUCES-MVSNE: 35.997 -> 26.628Improved
use noise-injected regression NiRNE instead of GenPerceptNiRNE · LUCES-MVNE: 28.050 -> 21.837Improved
use NiRNE instead of best diffusion method StableNormalNiRNE · LUCES-MVSNE: 37.045 -> 26.628Improved
bridge image-to-geometry with normal maps instead of direct Trellis generation (ablation)Hi3DGen · 3D generation (qualitative)visual fidelityImproved
use sharper accurate normals instead of smoother or wrong normals from other estimators (ablation)Hi3DGen · 3D generation (qualitative)visual fidelityImproved
add online normal regularization to latent diffusion (ablation)NoRLD · 3D generation (qualitative)visual fidelityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy